Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1327 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5698. Min Range: -7.5698
Max Act: 7.5698. Min Act: -0.1700
Data Index: 3927821 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5698. Min Range: -7.5698
Max Act: 7.5073. Min Act: -0.1700
Data Index: 6454083 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5698. Min Range: -7.5698
Max Act: 7.4448. Min Act: -0.1700
Data Index: 6321601 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5698. Min Range: -7.5698
Max Act: 7.1323. Min Act: -0.1700
Data Index: 7293663 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5698. Min Range: -7.5698
Max Act: 7.1011. Min Act: -0.1700
Data Index: 7951589 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5698. Min Range: -7.5698
Max Act: 7.0698. Min Act: -0.1700
Data Index: 3369492 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5698. Min Range: -7.5698
Max Act: 7.0698. Min Act: -0.1700
Data Index: 5719051 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5698. Min Range: -7.5698
Max Act: 7.0073. Min Act: -0.1700
Data Index: 8301405 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5698. Min Range: -7.5698
Max Act: 7.0386. Min Act: -0.1700
Data Index: 2097627 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5698. Min Range: -7.5698
Max Act: 6.9761. Min Act: -0.1700
Data Index: 7678902 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5698. Min Range: -7.5698
Max Act: 6.9448. Min Act: -0.1700
Data Index: 6506133 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5698. Min Range: -7.5698
Max Act: 6.8823. Min Act: -0.1700
Data Index: 5588736 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5698. Min Range: -7.5698
Max Act: 6.8823. Min Act: -0.1700
Data Index: 8324267 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5698. Min Range: -7.5698
Max Act: 6.8511. Min Act: -0.1700
Data Index: 3784988 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5698. Min Range: -7.5698
Max Act: 6.8823. Min Act: -0.1700
Data Index: 299421 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5698. Min Range: -7.5698
Max Act: 6.7886. Min Act: -0.1700
Data Index: 5514039 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5698. Min Range: -7.5698
Max Act: 6.7573. Min Act: -0.1700
Data Index: 6571751 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5698. Min Range: -7.5698
Max Act: 6.7261. Min Act: -0.1700
Data Index: 2894109 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5698. Min Range: -7.5698
Max Act: 6.6948. Min Act: -0.1700
Data Index: 2167199 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5698. Min Range: -7.5698
Max Act: 6.6948. Min Act: -0.1700
Data Index: 4988132 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19